© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88704
    Prev
    Next
    INDEX
    Explanations

    references to subscription services and their pricing models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ³
    -0.06
     rural
    -0.06
    iyel
    -0.06
    osy
    -0.06
     Qed
    -0.06
    ocument
    -0.06
    INLINE
    -0.05
    -national
    -0.05
    476
    -0.05
    rey
    -0.05
    POSITIVE LOGITS
     paid
    0.13
     Paid
    0.11
    paid
    0.11
    Paid
    0.11
    -paid
    0.09
    free
    0.08
     fee
    0.07
     free
    0.07
    _paid
    0.07
     commercial
    0.07
    Activations Density 0.024%

    No Known Activations